EP1083405A1 - Appareil à référence vocale, enregistreur, programme de commande d'enregistreur de de référence vocale et appareil de navigation à reconnaissance vocale - Google Patents

Appareil à référence vocale, enregistreur, programme de commande d'enregistreur de de référence vocale et appareil de navigation à reconnaissance vocale Download PDF

Info

Publication number
EP1083405A1
EP1083405A1 EP00307731A EP00307731A EP1083405A1 EP 1083405 A1 EP1083405 A1 EP 1083405A1 EP 00307731 A EP00307731 A EP 00307731A EP 00307731 A EP00307731 A EP 00307731A EP 1083405 A1 EP1083405 A1 EP 1083405A1
Authority
EP
European Patent Office
Prior art keywords
voice
recognition
division
division block
search target
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
EP00307731A
Other languages
German (de)
English (en)
Other versions
EP1083405B1 (fr
EP1083405B2 (fr
Inventor
Yoshikazu Hirayama
Yoshiyuki Kobayashi
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Faurecia Clarion Electronics Co Ltd
Original Assignee
Xanavi Informatics Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Family has litigation
First worldwide family litigation filed litigation Critical https://patents.darts-ip.com/?family=17286260&utm_source=google_patent&utm_medium=platform_link&utm_campaign=public_patent_search&patent=EP1083405(A1) "Global patent litigation dataset” by Darts-ip is licensed under a Creative Commons Attribution 4.0 International License.
Application filed by Xanavi Informatics Corp filed Critical Xanavi Informatics Corp
Publication of EP1083405A1 publication Critical patent/EP1083405A1/fr
Publication of EP1083405B1 publication Critical patent/EP1083405B1/fr
Application granted granted Critical
Publication of EP1083405B2 publication Critical patent/EP1083405B2/fr
Anticipated expiration legal-status Critical
Expired - Lifetime legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/36—Input/output arrangements for on-board computers
    • G01C21/3605—Destination input or retrieval
    • G01C21/3608—Destination input or retrieval using speech input, e.g. using speech recognition
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
    • G10L2015/226—Procedures used during a speech recognition process, e.g. man-machine dialogue using non-speech characteristics
    • G10L2015/228—Procedures used during a speech recognition process, e.g. man-machine dialogue using non-speech characteristics of application context

Definitions

  • the present invention relates to a voice reference system and a voice recognition navigation apparatus using the voice reference system.
  • navigation apparatuses There are car navigation apparatuses (hereafter referred to as navigation apparatuses) that display the current position of the vehicle, display a map over a wide area or in detail and provide guidance to the driver along the traveling direction over the remaining distance to the destination in the prior art.
  • voice recognition navigation apparatuses in the prior art having a function of enabling the driver engaged in driving to issue operating instructions by voice to improve driver safety (see Japanese Laid-Open Patent Publication No. 09-292255, for instance).
  • FIGS. 11A ⁇ 11D illustrate the concept of voice recognition dictionaries (hereafter simply referred to as dictionaries) used in a navigation apparatus in the prior art to display a desired ski resort in a map through voice instructions.
  • dictionaries voice recognition dictionaries
  • the basic dictionary shown in FIG. 11A is opened in the memory.
  • instruction phrases such as "bird's eye view display,” “enlarge,” “reduce” and “ski resorts” are stored as recognition words. If the user says (vocalizes) "ski resorts” to specify a facility category, voice recognition processing is performed on all the recognition words in the basic dictionary.
  • a ski resort prefecture name dictionary which contains prefecture names where ski resorts are present as recognition words is opened in memory, as shown in FIG. 11B.
  • the facility name dictionary in the wrong prefecture where the facility is not located is opened in memory and accessed.
  • An object of the present invention is to provide a voice reference apparatus capable of performing a search for a reference target through voice recognition quickly, efficiently and accurately with a high degree of reliability and a recording medium that records a control program used in the process. More specifically, the object of the present invention is to provide a voice recognition navigation apparatus capable of achieving accurate voice recognition of the names of facilities located near the borders of public administrative zones (districts).
  • a voice reference apparatus that classifies a plurality of search targets into a plurality of division blocks, searches for a search target by first specifying a division block and then specifying the search target and enables specification of, at least, the search target to be made by voice, comprises: a first storage device in which recognition data related to search targets corresponding to individual division blocks are stored; a second storage device in which division block-related information indicating one or more other division blocks related to a given division block through a specific relationship is stored; a recognition data selection device that selects recognition data corresponding to only a certain division block and one or more other division blocks related to the certain division block specified by the division block-related information from the first storage device, when the certain division block has been specified; and a voice recognition processing device that performs voice recognition based upon voice recognition data generated by using the recognition data selected by the recognition data selection device and audio data corresponding to the search target specified by voice.
  • the plurality of division blocks are public administrative zones; the search target is located in one of the public administrative zones; and the division block-related information indicates one or more other public administrative zones related to a specified public administrative zone through a specific relationship.
  • the public administrative zones are each constituted of a prefecture, a state or a country.
  • the division block-related information indicates one or more other public administrative zones adjacent to a specified public administrative zone.
  • the recognition data related to the search target includes information related to a public administrative zone in which the search target is located .
  • a display control device that implements control to display details related to results of a search of the search target on a display device is further provided, and when implementing control to display the details related to the results of the search of the search target, the display control device also displays on the display device information related to the public administrative zone in which the search target is located.
  • a voice recognition navigation apparatus comprises: a voice reference apparatus; a map information storage device that stores map information; and a control device that implements control for providing route guidance based upon, at least, results of a search performed by the voice reference apparatus and the map information.
  • the voice reference apparatus which classifies a plurality of search targets into a plurality of division blocks, searches for a search target by first specifying a division block and then specifying the search target and enables specification of, at least, the search target to be made by voice, comprises: a first storage device in which recognition data related to search targets corresponding to individual division blocks are stored; a second storage device in which division block-related information indicating one or more other division blocks related to a given division block through a specific relationship is stored; a recognition data selection device that selects recognition data corresponding to only a certain division block and one or more other division blocks related to the certain division block specified by the division block-related information from the first storage device, when the certain division block has been specified; and a voice recognition processing device that performs voice recognition based upon voice recognition data generated by using the recognition data selected by the recognition data selection device and audio data corresponding to the search target specified by voice.
  • a recording medium records the above voice reference control program.
  • a data signal according to the present invention comprises the above voice reference control program and is transmitted in a communication line.
  • FIG. 1 shows the structure adopted by the car navigation system in the first embodiment of the present invention.
  • the car navigation system comprises a navigation apparatus 100 and a voice unit 200.
  • the navigation apparatus 100 comprises a GPS receiver 101, a gyro sensor 102, a vehicle speed sensor 103, a driver 104, a CPU 105, a RAM 106, a ROM 107, a CD-ROM drive 108, a display device 109, a bus line 110 and the like.
  • the voice unit 200 comprises a microphone 201, an A/D conversion unit 202, a D/A conversion unit 203, an amplifier 204, a speaker 205, a TALK switch 206, a driver 207, a CPU 208, a RAM 209, a ROM 210, a bus line 212 and the like.
  • the navigation apparatus 100 and the voice unit 200 are connected with each other via a communication line 211.
  • the GPS receiver 101 receives a signal from a GPS (Global Positioning System) satellite and detects the absolute position and the absolute bearing of the vehicle.
  • the gyro sensor 102 which may be constituted of, for instance, a vibrating gyro, detects the yaw angle speed of the vehicle.
  • the vehicle speed sensor 103 detects the distance traveled by the vehicle based upon the number of pulses output each time the vehicle has traveled over a specific distance. The two dimensional movement of the vehicle is detected by the gyro sensor 102 and the vehicle speed sensor 103.
  • the driver 104 is provided to connect signals from the GPS receiver 101, the gyro sensor 102 and the vehicle speed sensor 103 with the bus line 110. In other words, the outputs from the individual sensors are converted to data that can be read by the CPU 105.
  • the CPU 105 controls the entire navigation apparatus 100 by executing a program stored in the ROM 107.
  • the RAM 106 which is constituted of volatile memory, a work data area is secured.
  • the ROM 107 constituted of non volatile memory, the control program mentioned above and the like are stored.
  • the CD-ROM drive 108 uses a CD-ROM 111 as a recording medium to store road map information such as vector road data and the like.
  • the CD-ROM drive may be alternatively constituted of another recording device such as a DVD drive which uses a DVD as a recording medium.
  • the display device 109 displays a road map that contains the current position and the surrounding area of the vehicle, route information indicating the route to the destination, the intersection information indicating the next intersection to which the vehicle is to be guided and the like. It may be constituted of, for instance, a liquid crystal display device or a CRT.
  • the bus line 110 is provided to connect the components of the navigation apparatus 100 such as the CPU 105 via a bus.
  • the voice unit 200 performs voice-related processing such as voice recognition and voice synthesis.
  • the TALK switch 206 is pressed by the user to give an instruction for a start of voice recognition. Audio data are input via the microphone 201 over a specific period of time after the TALK switch 206 is pressed. The sound thus input is converted to digital audio data by the A/D conversion unit 202 and the driver 207.
  • a voice recognition software program In the ROM 210 of the voice unit 200, a voice recognition software program, a voice synthesis software program, voice recognition dictionaries (hereafter simply referred to as recognition dictionaries), a voice synthesis dictionary (hereafter simply referred to as a synthesis dictionary) and the like are stored.
  • voice recognition software program correlation values between the digital audio data and all the recognition words in a recognition dictionary are calculated and the recognition word achieving a largest correlation value is determined to be the recognition results.
  • the voice synthesis program data needed to output a specified phrase through the speaker are calculated. Since both software programs are of the known art, their detailed explanation is omitted.
  • a recognition dictionary is constituted of a set of data compiled with a plurality of words and phrases to be used in voice recognition. More specifically, pronunciation data corresponding to individual words specified with Hiragana , Katakana, Roman characters or phonetic symbols (the corresponding character codes, in reality) are stored in the recognition dictionary. The words and phrases stored in the recognition dictionary are referred to as recognition words. The character data corresponding to the recognition word and information such as the corresponding coordinate information if the recognition word represents a facility name as well as the pronunciation data are attached to each recognition word. Details of the recognition dictionaries are to be given later. In the synthesis dictionary, sound source data and the like necessary for voice synthesis are stored.
  • the CPU 208 executes the voice recognition software program by using the RAM 209, the ROM 210 and the like to perform a voice recognition of the digital audio data.
  • the voice recognition software program references the pronunciation data (data specified in Hiragana, Katakana or Roman characters) of the recognition words in the recognition dictionary to generate the voice recognition data corresponding to the recognition words and calculates the correlation values between the voice recognition data and the digital audio data. It calculates the correlation values between all the recognition words and the digital audio data and determines the recognition word achieving the highest correlation value which is also equal to or larger than a specific value before ending the voice recognition.
  • the echo-back word linked to the recognition word is then converted to special speech data by using the voice synthesis software program. Then, the CPU 208 engages the D/A conversion unit 203, the amplifier 204 and the speaker 205 to output the recognition results through echo-back.
  • the CPU 208 decides that voice recognition has failed and thus no navigation operation is executed. More specifically, it may sound a beep indicating that a voice recognition attempt has failed or it may sound a response echo-back such as "recognition failed.”
  • the bus line 212 is provided for the voice unit 200.
  • the recognition dictionaries include a basic dictionary containing recognition words related to instructions, prefecture name dictionaries containing recognition words related to prefecture names corresponding to various categories and prefecture facility name dictionaries each containing recognition words related to the names of facilities in a given prefecture in a given category.
  • the prefecture names used to specify prefectures should be regarded as a type of instruction phrase.
  • FIGS. 2A ⁇ 2C show recognition dictionaries related to the ski resort category among the recognition dictionaries.
  • the basic dictionary shown in FIG. 2A is a dictionary commonly used among various categories, and contains recognition words related to instructions such as "bird's eye view display,” “enlarge ,” “reduce” and "ski resorts.”
  • the ski resort prefecture name dictionary shown in FIG. 2B recognition words related to the names of prefectures where ski resorts are present are stored.
  • the ABCD Prefecture ski resort name dictionary shown in FIG. 2C recognition words related to the names of ski resorts located in ABCD Prefecture are stored
  • the EFGH Prefecture ski resort name dictionary in FIG. 2C recognition words related to the names of ski resorts present in EFGH Prefecture are stored.
  • ski resort dictionaries corresponding to the individual prefectures listed in the ski resort prefecture name dictionary in FIG. 2B are provided.
  • a recognition word is constituted of pronunciation data for a given phrase, it is specified by hiragana, katakana, Roman character, pronunciation symbol or the like and the corresponding character code or the like is stored as the recognition word, the items in FIGS. 2A ⁇ 2C are expressed using Kanji and the like to facilitate the explanation.
  • the names of ski resorts in the entire country are stored in a hierarchical structure in units of individual prefectures for the following reason.
  • a single ski resort name dictionary in which the names of all the ski resorts in the country are stored, is provided without the ski resort prefecture name dictionary in FIG. 2B.
  • all the ski resort names in the recognition dictionary must undergo the voice recognition processing and a great deal of time will be required for the processing.
  • the entire recognition dictionary may not be opened in the memory at once due to limits imposed on the work memory capacity.
  • the names of ski resorts in the country are stored in the hierarchical structure in units of individual prefectures and are processed as described above.
  • a golf course prefecture name dictionary and golf course name dictionaries corresponding to the individual prefectures are prepared (not shown).
  • the dictionaries related to other categories such as theme parks are prepared in a similar manner.
  • recognition dictionaries the basic dictionary, prefecture dictionaries in various categories and facility name dictionaries corresponding to the individual prefectures in each category are prepared.
  • a neighboring prefecture table is stored in the ROM 210 in addition to the recognition dictionaries.
  • FIG. 3 presents the neighboring prefecture table
  • a neighboring prefecture table 301 contains neighboring prefecture information for each of the 47 prefectures in the country (in case of Japan).
  • Neighboring prefecture information 302 for each prefecture includes data indicating a prefecture code 303 which represents the target prefecture itself, the number of neighboring prefectures 304 and neighboring prefecture codes 305.
  • any of various methods may be adopted to assign neighboring prefectures. For instance, all the prefectures geographically adjacent to a given prefecture at its prefectural border may be assigned, prefectures that are considered to be nearby may be assigned, prefectures which should be regarded as neighboring prefectures as dictated by experience may be assigned or prefectures located along an expressway passing through the prefecture may be assigned as neighboring prefectures.
  • FIGS. 4A and 4B present an example of neighboring prefectures assigned for the individual prefectures in Japan.
  • the neighboring prefecture table described above is employed and the facility name dictionary corresponding to a neighboring prefecture of the specified prefecture, too, is opened in memory.
  • FIGS. 5 ⁇ 7 present a flowchart of the control implemented to search for the name of a facility located in a given prefecture on the voice unit 200.
  • ABCD Prefecture is erroneously specified when searching for F Ski Resort located in EFGH Prefecture adjacent to ABCD Prefecture.
  • the control program which is stored in the ROM 210, is executed by the CPU 208.
  • the routine is started up by turning on the power to the navigation apparatus 100 and the voice unit 200.
  • step S1 the basic dictionary shown in FIG. 2A stored in the ROM 210 is read out and opened in the RAM 209.
  • the basic dictionary in the ROM 210 is opened in the RAM 209 to increase the processing speed. If the processing speed is not a crucial issue, the dictionary in the ROM 210 may be accessed directly.
  • step S2 a decision is made as to whether or not the TALK switch 206 has been pressed, and if it is decided that the TALK switch 206 has been pressed, the operation proceeds to step S3. If, on the other hand, it is decided that the TALK switch 206 has not been pressed, the routine ends. After pressing the TALK switch 206, the user says (vocalizes), for instance, "ski resorts" within a specific period of time.
  • step S3 the audio signal obtained though the microphone 201 is converted to digital audio data.
  • step S4 a decision is made as to whether or not the speech has ended. A speech is judged to have ended when the audio signal lapses over a specific length of time. If it is decided that the speech has ended, the operation proceeds to step S5, whereas if it is decided that the speech has not ended, the operation returns to step S3. In this example, digital audio data corresponding to "ski resorts" are obtained in step S3.
  • step S5 the correlation values between the digital audio data that have been obtained and all the recognition words in the basic dictionary are calculated before the operation proceeds to step S6.
  • step S6 the correlation values between the digital audio data corresponding to "ski resorts” obtained in step S3 and the recognition words such as "bird's eye view display,” “enlarge,” “reduce,” “ski resorts” and “golf courses” are calculated.
  • step S6 a decision is made as to whether or not the largest correlation value among the calculated correlation values is equal to or larger than a specific value. If it is determined to be equal to or larger than the specific value, it is assumed that the word or phrase has been recognized and the operation proceeds to step S7. In this example, the correlation value relative to the recognition word "ski resorts" is the largest.
  • step S7 a voice message constituted of the recognition word that has achieved the largest correlation value and "say the prefecture name” is output.
  • a message "ski resorts,” "say the prefecture name” is echoed back by voice.
  • the prefecture name dictionary in the relevant category is prepared in the RAM 209 in step S7.
  • the "ski resort prefecture name dictionary" (see FIG. 2B) is opened in the RAM 209.
  • step S6 If, on the other hand, the largest correlation value is determined to be smaller than the specific value in step S6, it is assumed that the spoken word or phrase has not been recognized and the operation proceeds to step S8. In step S8, a voice message "recognition failed" is echoed back before the processing ends. The navigation apparatus 100 does not engage in any processing.
  • step S9 the audio signal obtained through the microphone 201 is converted to digital audio data as in step S3.
  • step S10 a decision is made as to whether not the speech has ended as in step S4. During this interval, the user says "ABCD Prefecture.” By repeating steps S9 and S10, the digital audio data corresponding to "ABCD Prefecture" are obtained in the example.
  • step S11 the correlation values between the digital audio data thus obtained and all the recognition words in the ski resort prefecture name dictionary are calculated before the operation proceeds to step S12. Namely, the correlation values between the digital audio data corresponding to "ABCD Prefecture” obtained in step S9 and the recognition words such as "Hokkaido,” “Aomori Prefecture,” “ABCD Prefecture,” “EFGH Prefecture” and “Okinawa Prefecture” are calculated.
  • step S12 a decision is made as to whether or not the largest correlation value among the calculated correlation values is equal to or larger than a specific value. If, it is decided to be equal to or larger than the specific value, it is concluded that the word has been recognized and the operation proceeds to step S13.
  • the correlation value relative to the recognition word "ABCD Prefecture” is the largest. If this correlation value is equal to or larger than the specific value, the phrase "ABCD Prefecture” has been recognized and the ski resort prefecture name has been successfully referenced.
  • a voice message constituted of the recognition word that has achieved the largest correlation value and "say the facility name” is output. In the example, "ABCD Prefecture. Say the facility name” is echoed back.
  • the facility name dictionary for the target prefecture and the facility name dictionary for a neighboring prefecture are opened in the RAM 209 in step S13. Since the name of the target prefecture has been obtained in step S12, the neighboring prefecture table (see FIG. 3) stored in the ROM 210 is accessed to obtain the neighboring prefecture information for the target prefecture. Based upon the neighboring prefecture information, the facility name dictionary corresponding to a neighboring prefecture is opened in the RAM 209. As a result, the target prefecture facility name dictionary and a neighboring prefecture facility name dictionary are incorporated and are prepared in the RAM 209 as if they constitute a single target prefecture facility name dictionary. In the example, in which EFGH Prefecture is a neighboring prefecture of ABCD Prefecture, "ABCD Prefecture ski resort name dictionary” and "EFGH ski resort name dictionary” are incorporated and prepared in the RAM 209.
  • the target prefecture facility name dictionary and the neighboring prefecture facility name dictionary alone may be accessed sequentially.
  • step S12 If, on the other hand, it is decided in step S12 that the largest correlation value is smaller than the specific value, it is decided that the spoken word or phrase has not been recognized and the operation proceeds to step S14.
  • step S14 a voice message "recognition failed" is echoed back and the processing ends. The navigation apparatus 100 does not engage in any processing.
  • step S15 the audio signal obtained through the microphone 201 is converted to digital audio data as in step S3.
  • step S16 a decision is made as to whether not the speech has ended as in step S4. The user says, for instance, "F Ski Resort” during this interval. While the F Ski Resort is actually located in EFGH Prefecture, the user erroneously believes that the F Ski Resort is in ABCD Prefecture, since it is located near the prefectural border of ABCD Prefecture and EFGH Prefecture. By repeating step S15 and step S16, the digital audio data corresponding to "F Ski Resort" are obtained.
  • step S17 the correlation values between the digital audio data that have been obtained and all the recognition words in the facility name dictionaries prepared in the RAM 209 are calculated, and the operation proceeds to step S18.
  • the facility name dictionary corresponding to the target prefecture and the facility name dictionary corresponding to the neighboring prefecture are prepared in the RAM 209, and the correlation values relative to all the recognition words in these dictionaries are calculated.
  • correlation values between the digital audio data corresponding to "F Ski Resort" obtained in step S15 and all the recognition words representing the ski resort names in the "ABCD Prefecture ski resort name dictionary” and the "EFGH Prefecture ski resort name dictionary” are calculated.
  • step S18 a decision is made as to whether or not the largest correlation value among the calculated correlation values is equal to or larger than a specific volume. If it is decided to be equal to or larger than the specific value, it is concluded that the word or phrase has been recognized and the operation proceeds to step S19.
  • the correlation value relative to the recognition word "F Ski Resort” in the EFGH Prefecture ski resort name dictionary is the largest. If this correlation value is equal to or larger than the specific value, the phrase "F Ski Resort” has been recognized and a successful search of the facility name has been achieved.
  • step S19 the recognition word "F Ski Resort” achieving the largest correlation value is echoed back.
  • step S19 the navigation apparatus 100 is notified that a valid facility name has been recognized before the processing ends. While the navigation apparatus 100 is notified, the coordinates of the facility on the map are also provided to the navigation apparatus 100. Additional information constituted of coordinate data indicating the coordinates of the corresponding facility is also stored in the recognition dictionary in correspondence to each recognition word. The navigation apparatus 100 displays a road map of the area around the facility on the display device 109 based upon the coordinate data indicating the coordinates of the facility on the map transmitted via the communication line 211.
  • step S18 If, on the other hand, the largest correlation value is determined to be smaller than the specific value in step S18, it is assumed that the spoken word has not been recognized and the operation proceeds to step S20.
  • step S20 "recognition failed" is echoed back by voice, before ending the processing.
  • the navigation apparatus 100 does not engage in any processing, either.
  • the facility can be referenced in a reliable manner.
  • the neighboring "ABCD Prefecture” when searching for "F Ski Resort” located in "EFGH Prefecture” “F Ski Resort” can be referenced with a high degree of reliability.
  • the target facility can be searched efficiently, quickly, accurately and reliably while requiring only a small work memory capacity.
  • the user inputs by voice the number he wishes to choose or inputs the number he wishes to choose through an input device (not shown) such as a remote control for the navigation apparatus.
  • an input device such as a remote control for the navigation apparatus.
  • FIGS. 8A ?? 8C show recognition dictionaries related to the ski resort category among recognition dictionaries, presenting an example in which the area is divided in units of individual states. They correspond to FIGS. 2A ?? 2C illustrating the first embodiment.
  • the ski resort state name dictionary shown in FIG. 8B recognition words corresponding to the names of states in which ski resorts are present are stored.
  • the ABCD State ski resort name dictionary contains recognition words corresponding to the names of ski resorts present in ABCD State
  • the EFGH State ski resort name dictionary contains recognition words corresponding to the names of ski resorts present in EFGH State.
  • Ski resort name dictionaries corresponding to all the states listed in the ski resort state name dictionary in FIG. 2B are provided in addition to the ABCD State ski resort name dictionary and the EFGH State ski resort name dictionary in FIG. 2C.
  • a recognition dictionary spelling and the voice recognition data (e.g., phonetic symbols (pronunciation symbols)) of recognition words to undergo voice recognition processing are stored. Also, as in the first embodiment, information such as coordinate information is attached in the case of facility names.
  • FIG. 9 shows a neighboring state table. It corresponds to FIG. 3 illustrating the first embodiment and is similar to FIG. 3 except for that the prefectures in FIG. 3 are replaced by the states.
  • the assignment of neighboring states may be made in a manner similar to the manner in which neighboring prefectures are assigned in the first embodiment.
  • Processing similar to that performed in the first embodiment is implemented by using the ski resort state name dictionary, the individual state ski resort name dictionary and the neighboring state table described above. Consequently, even if a neighboring state is specified by mistake when searching for a facility present in a given state, the target facility can be referenced with a high degree of reliability.
  • the area is divided in units of individual states in the United States.
  • the present invention may be adopted in conjunction with an area divided in units of public administrative zone units used in other countries.
  • recognition dictionaries can be prepared in correspondence to zones (e.g., states, prefectures, districts and countries) resulting from the divisions made in conformance to the particulars of zone boundaries in the individual countries.
  • zones e.g., states, prefectures, districts and countries
  • the area may be divided in units of individual countries, as well.
  • the present invention is not limited to this example. It may be adopted in portable navigation apparatuses instead of navigation apparatuses mounted in vehicles. In addition, it may be adopted in a guide system installed in a building as well. In short, it may be adopted in all types of systems or apparatuses on which a search target among a plurality of search targets present in a plurality of divided zones is specified by voice.
  • the present invention is not limited to this example, and the area may be divided in units of smaller municipalities or in units of individual regions such as the Kanto Region, the Tokai Region and the Kinki Region. In addition, it may be divided in units of individual floors or individual specific ranges on a given floor in the case of a guide system installed in a building.
  • the search blocks do not need to represent geographical divisions, either. For instance, if the basic dictionary in FIG. 2A contains a recognition word "Restaurants," the dictionary which is equivalent to the dictionary shown in FIG.
  • FIG. 2B may contain recognition words indicating different types of restaurants such as "French cuisine,” “Chinese cuisine” and “Japanese cuisine,” and the dictionaries that are equivalent to those in FIG. 2C may each contain the names of restaurants specializing in each cuisine.
  • the present invention may be adopted effectively when different types of "accommodations" are classified as “business hotels,” “hotels” and “Japanese-style inns.” In such a case, by assigning "business hotels” and “hotels” to classification categories that are similar to each other, a search can be performed with “business hotels” added as a search target when "hotels" is specified. Thus, even if "hotels” is erroneously specified to search for "ABC Hotel” which is classified as a business hotel, a successful search is achieved.
  • a ski resort located in a given public administrative zone the present invention is not limited to these particulars. Any targets, including street names, airport names and theme parks can be referenced.
  • a search target may assume any form and its classification block, too, may assume any form in correspondence to the attributes of the search target.
  • control program, the recognition dictionaries, the neighboring prefecture table and the like explained above may be provided in a recording medium such as the CD-ROM 111.
  • control program, the recognition dictionaries and the like may be provided in a recording medium such as a CD-ROM 111 and the system described above may be realized on a computer such as a personal computer or a workstation.
  • control program, the recognition dictionaries, the neighboring prefecture dictionaries and the like may be provided via a transmission medium such as a communication line, a typical example of which is the Internet.
  • the control program and the like may be converted to a signal that is transmitted through a transmission medium.
  • FIG. 10 illustrates how this may be realized.
  • a navigation apparatus 401 is the navigation apparatus explained earlier and has a function of connecting with a communication line 402.
  • a computer 403 is a server computer in which the control program and the like are stored so that the control program and the like can be provided to the 401.
  • the communication line 402 may be a communication line for Internet communication or personal computer communication, or it may be a dedicated communication line.
  • the communication line 402 may be a telephone line or a wireless telephone line such as that for a mobile telephone connection.
  • the navigation apparatus 100 displays a map of the area around the facility as part of the navigation processing which includes route guidance
  • the present invention is not limited to these particulars.
  • Various types of navigation processing such as route search and route guidance may be implemented in the navigation apparatus 100 based upon the results of a successful search performed by the voice unit 200.
  • a search may be performed by giving the highest priority to the specified prefecture with neighboring prefectures assigned with differing priority ranks.
  • a search may be started using the facility name dictionary corresponding to the prefecture with the highest priority, and the processing may be finished after completing the search if a correlation value achieving a level equal to or higher than a specific level is obtained in referencing the prefecture.
  • search target is specified through voice recognition
  • present invention is not restricted by these particulars. It may be adopted when a search target is specified through an input device such as a keyboard, as well. In other words, it may be adopted in all modes of a search executed in units of specific classification blocks instead of handling all the search targets at once.

Landscapes

  • Engineering & Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Physics & Mathematics (AREA)
  • Acoustics & Sound (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • General Health & Medical Sciences (AREA)
  • Human Computer Interaction (AREA)
  • Artificial Intelligence (AREA)
  • Health & Medical Sciences (AREA)
  • Automation & Control Theory (AREA)
  • General Physics & Mathematics (AREA)
  • Navigation (AREA)
  • Traffic Control Systems (AREA)
EP00307731.0A 1999-09-09 2000-09-07 Appareil à référence vocale, enregistreur, programme de commande d'enregistreur de de référence vocale et appareil de navigation à reconnaissance vocale Expired - Lifetime EP1083405B2 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP25598199A JP4642953B2 (ja) 1999-09-09 1999-09-09 音声検索装置、および、音声認識ナビゲーション装置
JP25598199 1999-09-09

Publications (3)

Publication Number Publication Date
EP1083405A1 true EP1083405A1 (fr) 2001-03-14
EP1083405B1 EP1083405B1 (fr) 2003-04-16
EP1083405B2 EP1083405B2 (fr) 2013-07-10

Family

ID=17286260

Family Applications (1)

Application Number Title Priority Date Filing Date
EP00307731.0A Expired - Lifetime EP1083405B2 (fr) 1999-09-09 2000-09-07 Appareil à référence vocale, enregistreur, programme de commande d'enregistreur de de référence vocale et appareil de navigation à reconnaissance vocale

Country Status (4)

Country Link
US (1) US6950797B1 (fr)
EP (1) EP1083405B2 (fr)
JP (1) JP4642953B2 (fr)
DE (1) DE60002140T2 (fr)

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1193959A2 (fr) * 2000-09-05 2002-04-03 Pioneer Corporation Dictionnaires hiérarchisés pour la reconnaissance de la parole
EP1273886A1 (fr) * 2001-07-06 2003-01-08 Robert Bosch Gmbh Système et procédé de navigation pour un véhicule
DE10143292A1 (de) * 2001-09-04 2003-03-20 Deutsche Telekom Ag Sprachfenster
EP1505573A1 (fr) * 2002-05-10 2005-02-09 Asahi Kasei Kabushiki Kaisha Dispositif de reconnaissance vocale
EP1742019A1 (fr) * 2004-04-30 2007-01-10 Pioneer Design Corporation Dispositif de recherche de point, dispositif de navigation, procede de recherche de point, programme de recherche de point, et support d'enregistrement d'informations dans lequel le programme de recherche de point est enregistre
US20070276586A1 (en) * 2006-05-25 2007-11-29 Samsung Electronics Co., Ltd. Method of setting a navigation terminal for a destination and an apparatus therefor
EP2171710A2 (fr) * 2007-07-11 2010-04-07 Garmin Ltd. Décomposition en carreaux de données de reconnaissance automatique de la parole (asr)
CN116684327A (zh) * 2023-08-03 2023-09-01 中维建技术有限公司 一种基于云计算的山林地区通信网络故障监测评估方法

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP3576511B2 (ja) * 2001-09-19 2004-10-13 松下電器産業株式会社 音声対話装置
JP2006139203A (ja) * 2004-11-15 2006-06-01 Mitsubishi Electric Corp 施設検索装置
JP4822993B2 (ja) * 2006-09-11 2011-11-24 アルパイン株式会社 地点探索装置及びナビゲーション装置
JP5187128B2 (ja) * 2008-10-16 2013-04-24 富士通株式会社 検索装置、検索方法、及び、プログラム
GB201421441D0 (en) * 2014-12-02 2015-01-14 Tomtom Int Bv Method and apparatus for providing point of interest information
GB201421442D0 (en) 2014-12-02 2015-01-14 Tomtom Int Bv Method and apparatus for providing point of interest information

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0633452A1 (fr) * 1993-07-07 1995-01-11 Aisin Aw Co., Ltd. Système de navigation
EP0768638A2 (fr) * 1995-10-16 1997-04-16 Sony Corporation Dispositif et procédé de reconnaissance de la parole, de visualisation de cartes et de navigation
DE19717601A1 (de) * 1996-04-26 1997-10-30 Pioneer Electronic Corp Navigationsverfahren und Vorrichtung dafür

Family Cites Families (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2946269B2 (ja) 1993-08-25 1999-09-06 本田技研工業株式会社 車載情報処理用音声認識装置
JP3468824B2 (ja) 1994-03-29 2003-11-17 本田技研工業株式会社 車両誘導装置
JPH08328584A (ja) * 1995-05-29 1996-12-13 Sony Corp 音声認識装置、音声認識方法及びナビゲーション装置
US6067521A (en) * 1995-10-16 2000-05-23 Sony Corporation Interrupt correction of speech recognition for a navigation device
JP3605682B2 (ja) * 1996-05-16 2004-12-22 本田技研工業株式会社 音声入力制御装置
JPH1019194A (ja) * 1996-07-01 1998-01-23 Hitachi Ltd 高温圧力容器
JP3186655B2 (ja) * 1996-07-31 2001-07-11 アイシン・エィ・ダブリュ株式会社 車両用ナビゲーション装置及び記憶媒体
JPH1062199A (ja) * 1996-08-23 1998-03-06 Toyota Motor Corp 音声認識装置
JP3627489B2 (ja) * 1997-12-24 2005-03-09 トヨタ自動車株式会社 ナビゲーション用音声認識装置および音声認識機能付きナビゲーション装置
JPH11184880A (ja) * 1997-12-24 1999-07-09 Sharp Corp 音声認識装置及びコンピュータ読み取り可能な記録媒体
US6081803A (en) * 1998-02-06 2000-06-27 Navigation Technologies Corporation Support for alternative names in a geographic database used with a navigation program and methods for use and formation thereof
US6073076A (en) * 1998-03-27 2000-06-06 Navigation Technologies Corporation Memory management for navigation system
US6173279B1 (en) * 1998-04-09 2001-01-09 At&T Corp. Method of using a natural language interface to retrieve information from one or more data resources
US6184823B1 (en) * 1998-05-01 2001-02-06 Navigation Technologies Corp. Geographic database architecture for representation of named intersections and complex intersections and methods for formation thereof and use in a navigation application program
JP3759313B2 (ja) * 1998-05-15 2006-03-22 松下電器産業株式会社 車載用ナビゲーション装置
US6122593A (en) * 1999-08-03 2000-09-19 Navigation Technologies Corporation Method and system for providing a preview of a route calculated with a navigation system
US6292745B1 (en) * 2000-07-24 2001-09-18 Navigation Technologies Corp. Method and system for forming a database of geographic data for distribution to navigation system units

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0633452A1 (fr) * 1993-07-07 1995-01-11 Aisin Aw Co., Ltd. Système de navigation
EP0768638A2 (fr) * 1995-10-16 1997-04-16 Sony Corporation Dispositif et procédé de reconnaissance de la parole, de visualisation de cartes et de navigation
DE19717601A1 (de) * 1996-04-26 1997-10-30 Pioneer Electronic Corp Navigationsverfahren und Vorrichtung dafür

Cited By (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1193959A3 (fr) * 2000-09-05 2002-12-18 Pioneer Corporation Dictionnaires hiérarchisés pour la reconnaissance de la parole
EP1193959A2 (fr) * 2000-09-05 2002-04-03 Pioneer Corporation Dictionnaires hiérarchisés pour la reconnaissance de la parole
EP1273886A1 (fr) * 2001-07-06 2003-01-08 Robert Bosch Gmbh Système et procédé de navigation pour un véhicule
DE10143292A1 (de) * 2001-09-04 2003-03-20 Deutsche Telekom Ag Sprachfenster
DE10143292B4 (de) * 2001-09-04 2015-06-03 Deutsche Telekom Ag Sprachfenster
US7487091B2 (en) 2002-05-10 2009-02-03 Asahi Kasei Kabushiki Kaisha Speech recognition device for recognizing a word sequence using a switching speech model network
EP1505573A1 (fr) * 2002-05-10 2005-02-09 Asahi Kasei Kabushiki Kaisha Dispositif de reconnaissance vocale
EP1505573A4 (fr) * 2002-05-10 2005-07-13 Asahi Chemical Ind Dispositif de reconnaissance vocale
EP1742019A1 (fr) * 2004-04-30 2007-01-10 Pioneer Design Corporation Dispositif de recherche de point, dispositif de navigation, procede de recherche de point, programme de recherche de point, et support d'enregistrement d'informations dans lequel le programme de recherche de point est enregistre
EP1742019A4 (fr) * 2004-04-30 2012-01-25 Pioneer Corp Dispositif de recherche de point, dispositif de navigation, procede de recherche de point, programme de recherche de point, et support d'enregistrement d'informations dans lequel le programme de recherche de point est enregistre
EP1860405A3 (fr) * 2006-05-25 2013-01-16 Samsung Electronics Co., Ltd. Procédé de réglage d'un terminal de navigation pour une destination et appareil correspondant
US20070276586A1 (en) * 2006-05-25 2007-11-29 Samsung Electronics Co., Ltd. Method of setting a navigation terminal for a destination and an apparatus therefor
EP2171710A2 (fr) * 2007-07-11 2010-04-07 Garmin Ltd. Décomposition en carreaux de données de reconnaissance automatique de la parole (asr)
EP2171710A4 (fr) * 2007-07-11 2013-06-19 Garmin Switzerland Gmbh Décomposition en carreaux de données de reconnaissance automatique de la parole (asr)
CN116684327A (zh) * 2023-08-03 2023-09-01 中维建技术有限公司 一种基于云计算的山林地区通信网络故障监测评估方法

Also Published As

Publication number Publication date
DE60002140D1 (de) 2003-05-22
EP1083405B1 (fr) 2003-04-16
JP4642953B2 (ja) 2011-03-02
US6950797B1 (en) 2005-09-27
DE60002140T2 (de) 2004-01-29
EP1083405B2 (fr) 2013-07-10
JP2001083988A (ja) 2001-03-30

Similar Documents

Publication Publication Date Title
US6108631A (en) Input system for at least location and/or street names
US6836822B1 (en) Apparatus for and method of retrieving information
US6067521A (en) Interrupt correction of speech recognition for a navigation device
EP1083405B1 (fr) Appareil à référence vocale, enregistreur, programme de commande d'enregistreur de de référence vocale et appareil de navigation à reconnaissance vocale
US20030014261A1 (en) Information input method and apparatus
US6064323A (en) Navigation apparatus, navigation method and automotive vehicles
US20010037203A1 (en) Navigation system
US20060253251A1 (en) Method for street name destination address entry using voice
US20080228712A1 (en) Search Data Update Method and Search Data Update System
EP2000774A1 (fr) Appareil et programme de navigation
JPH11271084A (ja) 車両用ナビゲーション装置及び記憶媒体
JPH10111141A (ja) 車両用ナビゲーション装置
JP3892338B2 (ja) 単語辞書登録装置および単語登録用プログラム
EP0827124B1 (fr) Système de navigation pour véhicule avec accélération de la sélection du nom de ville et stockage des programmes à cet effet
JP3818352B2 (ja) ナビゲーション装置及び記憶媒体
US20040015354A1 (en) Voice recognition system allowing different number-reading manners
JP5004026B2 (ja) 文字選択装置、ナビゲーション装置、及び文字選択プログラム
JP4295674B2 (ja) ナビゲーション装置及びナビゲーションプログラム
JP2007065206A (ja) 施設検索装置
WO2006028171A1 (fr) Dispositif de présentation de données, méthode de présentation de données, programme de présentation de données et support d’enregistrement contenant le programme
JP2000074685A (ja) 車載装置における検索方法と車載ナビゲーション装置
JP2002108389A (ja) 音声による個人名称検索、抽出方法およびその装置と車載ナビゲーション装置
JP2006243730A (ja) 地図検索装置及び地図検索方法等
JP2003021530A (ja) 音声によるエリア内施設検索方法および装置
JP3506584B2 (ja) 情報検索装置及びナビゲーション装置における情報入力装置、並びに情報検索方法、並びにナビゲーション装置における情報入力制御プログラムが記録されたコンピュータ読み取り可能な記録媒体

Legal Events

Date Code Title Description
PUAI Public reference made under article 153(3) epc to a published international application that has entered the european phase

Free format text: ORIGINAL CODE: 0009012

17P Request for examination filed

Effective date: 20000920

AK Designated contracting states

Kind code of ref document: A1

Designated state(s): DE FR GB

AX Request for extension of the european patent

Free format text: AL;LT;LV;MK;RO;SI

AKX Designation fees paid

Free format text: DE FR GB

17Q First examination report despatched

Effective date: 20020123

GRAH Despatch of communication of intention to grant a patent

Free format text: ORIGINAL CODE: EPIDOS IGRA

GRAH Despatch of communication of intention to grant a patent

Free format text: ORIGINAL CODE: EPIDOS IGRA

GRAA (expected) grant

Free format text: ORIGINAL CODE: 0009210

AK Designated contracting states

Designated state(s): DE FR GB

REG Reference to a national code

Ref country code: GB

Ref legal event code: FG4D

REF Corresponds to:

Ref document number: 60002140

Country of ref document: DE

Date of ref document: 20030522

Kind code of ref document: P

ET Fr: translation filed
PLBI Opposition filed

Free format text: ORIGINAL CODE: 0009260

PLAX Notice of opposition and request to file observation + time limit sent

Free format text: ORIGINAL CODE: EPIDOSNOBS2

26 Opposition filed

Opponent name: DAIMLERCHRYSLER AG

Effective date: 20040105

PLAX Notice of opposition and request to file observation + time limit sent

Free format text: ORIGINAL CODE: EPIDOSNOBS2

PLBB Reply of patent proprietor to notice(s) of opposition received

Free format text: ORIGINAL CODE: EPIDOSNOBS3

PUAH Patent maintained in amended form

Free format text: ORIGINAL CODE: 0009272

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: PATENT MAINTAINED AS AMENDED

27A Patent maintained in amended form

Effective date: 20130710

AK Designated contracting states

Kind code of ref document: B2

Designated state(s): DE FR GB

REG Reference to a national code

Ref country code: DE

Ref legal event code: R102

Ref document number: 60002140

Country of ref document: DE

REG Reference to a national code

Ref country code: DE

Ref legal event code: R102

Ref document number: 60002140

Country of ref document: DE

Effective date: 20130710

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: DE

Payment date: 20130904

Year of fee payment: 14

REG Reference to a national code

Ref country code: DE

Ref legal event code: R135

Ref document number: 60002140

Country of ref document: DE

Effective date: 20131011

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: DE

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20131011

REG Reference to a national code

Ref country code: GB

Ref legal event code: 732E

Free format text: REGISTERED BETWEEN 20140417 AND 20140423

REG Reference to a national code

Ref country code: FR

Ref legal event code: TP

Owner name: CLARION CO., LTD., JP

Effective date: 20140604

REG Reference to a national code

Ref country code: FR

Ref legal event code: PLFP

Year of fee payment: 16

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: GB

Payment date: 20150902

Year of fee payment: 16

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: FR

Payment date: 20150811

Year of fee payment: 16

GBPC Gb: european patent ceased through non-payment of renewal fee

Effective date: 20160907

REG Reference to a national code

Ref country code: FR

Ref legal event code: ST

Effective date: 20170531

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: GB

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20160907

Ref country code: FR

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20160930